Abstract: The disclosure herein enables tracking of multiple objects in a real-time video stream. For each individual frame received from the video stream, a frame type of the frame is determined. Based on the individual frame being an object detection frame type, a set of object proposals is detected in the individual frame, associations between the set of object proposals and a set of object tracks are assigned, and statuses of the set of object tracks are updated based on the assigned associations. Based on the individual frame being an object tracking frame type, single-object tracking is performed on the frame based on each object track of the set of object tracks and the set of object tracks is updated based on the performed single-object tracking. For each frame received, a real-time object location data stream is provided based on the set of object tracks.

Abstract: A photoelectrical device for detection of bacterial cell density includes a substrate, a driving electrode layer, an AC power source and a photoelectric conversion layer. The driving electrode layer is disposed on the substrate and includes a central electrode and a peripheral electrode pattern surrounding the central electrode. A fluid sample is disposed on the driving electrode layer. The AC power source is electrically connected to the driving electrode layer, and used to produce a non-uniform alternating electric field in the fluid sample on the driving electrode layer for driving the target bioparticles to gather up on the central electrode to form a particle cluster. The photoelectric conversion layer is used for receiving a light detecting beam after passing through the particle cluster and outputting an electric current based on the optical density of light detecting beam. The electric current changes as a concentration of the target bioparticles changes.

Abstract: The speech correction system includes a storage device, an audio receiver and a processing device. The processing device includes a speech recognition engine and a determination module. The storage device is configured to store a database. The audio receiver is configured to receive an audio signal. The speech recognition engine is configured to identify a key speech pattern in the audio signal and generate a candidate vocabulary list and a transcode corresponding to the key speech pattern; wherein the candidate vocabulary list includes a candidate vocabulary corresponding to the key speech pattern and a vocabulary score corresponding to the candidate vocabulary. The determination module is configured to determine whether the vocabulary score is greater than a score threshold. If the vocabulary score is greater than the score threshold, the determination module stores the candidate vocabulary corresponding to the vocabulary score in the database.

Abstract: A plasticizer, which is biodegradable, has a molecule including a central structure, at least two connecting structures and at least one side-chain structure. The central structure includes at least one of a benzene derivative and at least one amino acid. The connecting structures are respectively connected to the central structure, wherein the connecting structures include a first connecting structure and a second connecting structure. The first connecting structure is an amine group, and the second connecting structure is a carboxyl group. The side-chain structure is a chain of multiple carbon atoms, and the side-chain structure is connected to at least one of the first connecting structure and the second connecting structure. An amide bond is formed as the side-chain structure connected to the amine group, and an ester bond is formed as the side-chain structure connected to the carboxyl group.

Abstract: A pattern recognition method of the immunofluorescence images of autoantibody identification is disclosed. The method includes the following steps: inputting a plurality of original cell immunofluorescence images; conducting an operation of a plurality of convolutional neural networks by a processor, the plurality of convolutional neural networks include a convolution layer, a pooling layer and an inception layer for capturing the plurality of convolution features; conducting a judgment process to obtain the proportions of the antinuclear antibodies morphological patterns; and outputting the recognition results.

Abstract: A classification system and a classification method of the autoantibody immunofluorescence image are disclosed. The system includes an input device, a processor and an output device. The plurality of cell immunofluorescence images and the corresponded extractable nuclear antigen results are input through the input device. The processor conducts a plurality of convolution neural network calculation and output the classification based on the extractable nuclear antigen results, so as to obtain an extractable nuclear antigen classification model. When the autoantibody immunofluorescence image is input by the input device, the corresponded classification of the extractable nuclear antigen can be predicted. The classification result is output through the output device.

Abstract: The speech correction system includes a storage device and a processing device. The storage device stores a first database. The processing device includes an audio receiver, a speech recognition engine, a calculation module, and a determination module. The audio receiver receives multiple voice inputs. The speech recognition engine recognizes the voice inputs, generates multiple candidate vocabularies corresponding to each of the voice inputs, and generates a vocabulary probability corresponding to each of the candidate vocabularies. The calculation module performs a specific operation on the vocabulary probabilities corresponding to the same candidate vocabulary, to generate a plurality of corresponding operation results. The determination module determines whether each of the operation results is greater than a score threshold, and stores at least one output result that is greater than the score threshold to the first database.

Abstract: A method for improving the efficiency of reconstructing a three-dimensional model is provided. The method includes: dividing a series of different Gray code binary illumination patterns into a plurality of groups; converting binary values of Gray code binary illumination patterns in each group to a plurality of sets of two specific values to generate decimal illumination patterns corresponding to the specific values; overlapping the decimal illumination patterns in each group to a grayscale illumination pattern; using a projector to project each grayscale illumination pattern onto an object from a projection direction; using a camera to capture one or more object images of the object; reverting the object images to non-overlapping Gray code binary images corresponding to the object images; and reconstructing the depth of the object according to the non-overlapping Gray code binary images.

Abstract: A photoelectrical device for detection of bacterial cell density includes a substrate, a driving electrode layer, an AC power source and a photoelectric conversion layer. The driving electrode layer is disposed on the substrate and includes a central electrode and a peripheral electrode pattern surrounding the central electrode. A fluid sample is disposed on the driving electrode layer. The AC power source is electrically connected to the driving electrode layer, and used to produce a non-uniform alternating electric field in the fluid sample on the driving electrode layer for driving the target bioparticles to gather up on the central electrode to form a particle cluster. The photoelectric conversion layer is used for receiving a light detecting beam after passing through the particle cluster and outputting an electric current based on the optical density of light detecting beam. The electric current changes as a concentration of the target bioparticles changes.

Abstract: A lighting system and a driving circuit thereof are provided. The driving circuit is configured to drive a light emitting device. The driving circuit includes a bulk voltage converter. The bulk voltage converter receives an input voltage and converts the input voltage to generate a driving voltage. The bulk voltage converter includes a snubber circuit, a power switch, and an inductor. The snubber circuit receives the input voltage through a first node and generates a snubber voltage at a second node according to the input voltage. The power switch is turned on or off according to a control signal. The inductor is coupled between the first node and a third node. The driving circuit is coupled to the light emitting device through the first node and the third node and provides the driving voltage to the light emitting device.

Abstract: The speech correction system includes a storage device and a processing device. The storage device stores a first database. The processing device includes an audio receiver, a speech recognition engine, a calculation module, and a determination module. The audio receiver receives multiple voice inputs. The speech recognition engine recognizes the voice inputs, generates multiple candidate vocabularies corresponding to each of the voice inputs, and generates a vocabulary probability corresponding to each of the candidate vocabularies. The calculation module performs a specific operation on the vocabulary probabilities corresponding to the same candidate vocabulary, to generate a plurality of corresponding operation results. The determination module determines whether each of the operation results is greater than a score threshold, and stores at least one output result that is greater than the score threshold to the first database.

Abstract: The speech correction system includes a storage device, an audio receiver and a processing device. The processing device includes a speech recognition engine and a determination module. The storage device is configured to store a database. The audio receiver is configured to receive an audio signal. The speech recognition engine is configured to identify a key speech pattern in the audio signal and generate a candidate vocabulary list and a transcode corresponding to the key speech pattern; wherein the candidate vocabulary list includes a candidate vocabulary corresponding to the key speech pattern and a vocabulary score corresponding to the candidate vocabulary. The determination module is configured to determine whether the vocabulary score is greater than a score threshold. If the vocabulary score is greater than the score threshold, the determination module stores the candidate vocabulary corresponding to the vocabulary score in the database.

Abstract: A lighting system and a driving circuit thereof are provided. The driving circuit is configured to drive a light emitting device. The driving circuit includes a bulk voltage converter. The bulk voltage converter receives an input voltage and converts the input voltage to generate a driving voltage. The bulk voltage converter includes a snubber circuit, a power switch, and an inductor. The snubber circuit receives the input voltage through a first node and generates a snubber voltage at a second node according to the input voltage. The power switch is turned on or off according to a control signal. The inductor is coupled between the first node and a third node. The driving circuit is coupled to the light emitting device through the first node and the third node and provides the driving voltage to the light emitting device.

Abstract: A classification system and a classification method of the autoantibody immunofluorescence image are disclosed. The system includes an input device, a processor and an output device. The plurality of cell immunofluorescence images and the corresponded extractable nuclear antigen results are input through the input device. The processor conducts a plurality of convolution neural network calculation and output the classification based on the extractable nuclear antigen results, so as to obtain an extractable nuclear antigen classification model. When the autoantibody immunofluorescence image is input by the input device, the corresponded classification of the extractable nuclear antigen can be predicted. The classification result is output through the output device.

Abstract: A method for improving the efficiency of reconstructing a three-dimensional model is provided. The method includes: dividing a series of different Gray code binary illumination patterns into a plurality of groups; converting binary values of Gray code binary illumination patterns in each group to a plurality of sets of two specific values to generate decimal illumination patterns corresponding to the specific values; overlapping the decimal illumination patterns in each group to a grayscale illumination pattern; using a projector to project each grayscale illumination pattern onto an object from a projection direction; using a camera to capture one or more object images of the object; reverting the object images to non-overlapping Gray code binary images corresponding to the object images; and reconstructing the depth of the object according to the non-overlapping Gray code binary images..

Abstract: A pattern recognition method of the immunofluorescence images of autoantibody identification is disclosed. The method includes the following steps: inputting a plurality of original cell immunofluorescence images; conducting an operation of a plurality of convolutional neural networks by a processor, the plurality of convolutional neural networks include a convolution layer, a pooling layer and an inception layer for capturing the plurality of convolution features; conducting a judgment process to obtain the proportions of the antinuclear antibodies morphological patterns; and outputting the recognition results.

Abstract: A power adapter including a first substrate, a second substrate, a transformer and an insulating frame is provided. The first substrate includes a first terminal set. The second substrate includes a second terminal set. The transformer includes a primary side connection terminal and a secondary side connection terminal, wherein the primary side connection terminal is connected to the first terminal set and the secondary side connection terminal is connected to the second terminal set. The insulating frame is disposed between the first substrate and the second substrate, and the transformer leans against the insulating frame.

Abstract: A power adapter including a first substrate, a second substrate, a transformer and an insulating frame is provided. The first substrate includes a first terminal set. The second substrate includes a second terminal set. The transformer includes a primary side connection terminal and a secondary side connection terminal, wherein the primary side connection terminal is connected to the first terminal set and the secondary side connection terminal is connected to the second terminal set. The insulating frame is disposed between the first substrate and the second substrate, and the transformer leans against the insulating frame.

Abstract: According to embodiments of the disclosure, a substrate structure, a method for manufacturing the substrate structure, and a method for manufacturing an electronic device are disclosed. The substrate structure includes a carrier, a de-bonding layer, and a flexible substrate. The carrier has a top surface. The de-bonding layer contacts the carrier, wherein there is a first adhesion force between the de-bonding layer and the carrier. The de-bonding layer is prepared from a composition, and the composition includes at least one acrylate-based monomer and at least one acrylate-based oligomer, wherein the total number of acrylate groups in the acrylate-based monomer and the acrylate-based oligomer is greater than or equal to 3. The flexible substrate covers and contacts the de-bonding layer, wherein there is a second adhesion force between the de-bonding layer and the flexible substrate. The second adhesion force is greater than the first adhesion force.